© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3020
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inclusion or addition

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as well," indicating the inclusion or addition of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anos
    -0.73
    auri
    -0.68
    bley
    -0.67
    abies
    -0.62
    nce
    -0.62
    anon
    -0.62
     Fired
    -0.61
    atten
    -0.60
    rome
    -0.60
    mber
    -0.60
    POSITIVE LOGITS
    س
    0.64
    Parameters
    0.63
     as
    0.62
    onse
    0.62
    FTWARE
    0.61
     known
    0.60
    Param
    0.59
     evidenced
    0.59
     served
    0.58
     antioxid
    0.56
    Activations Density 0.033%

    No Known Activations